Anomalies in power consumption
For the internal development of data science know-how, modelling approaches for the detection of anomalies are developed in a hackathon.
staff are introduced to data science and machine learning.
Approaches and methods for detecting anomalies in electricity consumption identified.
Necessary data science skills identified for further projects
Challenge
An energy company is currently setting up a department that will serve as a hub for data science topics in the future and would like to use an initial use case to gain insights into the design of data science teams. Within the framework of this use case Anomalies in power consumption be uncovered in an automated and scalable way.
Solution
In a two-day hackathon, different models for the detection of anomalies are applied together with the client's employees. The power consumption of the markets is analysed with scatter, GAM and time series models, as well as various Machine Learning Algorithms estimated. On the basis of the estimates Thresholds for anomalies determined and identified.
Result
Within the framework of a feasibility study, various methodological approaches to the Anomaly detection tried out and evaluated. In addition, the client receives insights into the skillset required for Machine Learning and Data Science Project.
Are you interested in your own use cases?
Our Case Studies
- Get even more detailed insights into our customer projects -
Smart cooking with the Thermomix
Data Operations at Munich Re
Data & AI Knowledge
Creating added value from data & AI together